Open AccessAn Accurate Fall Detection System for the Elderly People Using Smartphone Inertial Sensors
Author(s) -
Abdul Amir H. Kadhum,
Hilal Al-Libawy,
Ehab AbdulRazzaq Hussein
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1530/1/012102
Subject(s) - accelerometer , gyroscope , support vector machine , computer science , artificial intelligence , inertial measurement unit , classifier (uml) , falling (accident) , artificial neural network , activity recognition , machine learning , real time computing , engineering , medicine , environmental health , aerospace engineering , operating system
In developed countries, the number of elderly people living alone is continuously increasing. These people are more vulnerable to serious health issues, such as falling down. A sensor-based system, augmented to mobile phones, can provide a much-needed prediction to the falls, where injuries and fracture possibilities can be significantly decreased. The purpose of this study is to develop a fall recognition system based on smartphone inertial sensors, which is a combination of accelerometer and gyroscope. The system can distinguish between falls and other activity daily livings (ADLs). The data output from the inertial sensor have been used by two different classifiers; artificial neural network (ANN) and support vector machine (SVM), where the objective is to find an accurate falling classifier using smartphone inertial sensors. Results show that SVM based classifier offers an accuracy of 99.27%, which outperforms the state of the art results that use smartphone data.